AI

Google Brings Gemini Computer Use Automation to macOS Users

Google announced a new computer use capability for the Gemini desktop app on macOS, letting the AI automate tasks in the background.

Christopher Clark
Christopher Clark covers software & saas for Techawave.
1 min read
Google Brings Gemini Computer Use Automation to macOS Users
Share

On Thursday, Google announced a new computer use capability for its Gemini desktop application on macOS, enabling the artificial intelligence to handle repetitive tasks, navigate native applications, and browse websites in the background on behalf of users. The feature allows Gemini to execute multistep workflows involving local files, applications, and the web following a user instruction.

While competing AI developers have already introduced agentic desktop features, Google is rolling out this new macOS capability initially in English in the U.S. Users can watch the agent operate through a live preview inside the chat interface while maintaining control of their cursor and screen for other work. Safety controls allow individuals to pause, stop, or approve actions before execution.

Expanding AI Agent Capabilities on macOS

The new functionality is designed to assist with tedious workflows, such as filling out forms, organizing files into folders based on specific criteria, repeating processes across multiple files, and generating slideshows from local documents or online dashboards. Accessing the new computer use feature requires the Gemini app for Mac alongside a Google AI Plus, Pro, or Ultra subscription.

This rollout follows other recent agentic developments from Google, including the broader rollout of the in-app “Tasks” feature to help users make purchases, sign into websites, or book appointments, alongside an early tester release of a revamped AI agent designed to help families organize emails, calendars, and chats.

Share